The BonFIRE Project supports experimentation and testing of innovative scenarios from the Internet of Services research community, specifically focused on the convergence of services and networks. BonFIRE operates a Cloud facility based on an Infrastructure as a Service delivery model with guidelines, policies and best practices for experimentation. A federated multi-platform approach is adopted, providing interconnection and interoperation between novel service and networking testbeds.

Geographically distributed testbeds

BonFIRE currently comprises 6 geographically distributed testbeds across Europe, which offer heterogeneous Cloud resources, including compute, storage and networking. Each testbed can be accessed seamlessly with a single experiment descriptor, using the BonFIRE API which is based on OCCI. See the image below for details about resource offering on the different testbeds, which include on-demand resources. For more information about the testbeds, please click [here].

As part of the BonFIRE project, we are also studying the possible federation of the BonFIRE testbeds with a variety of external cloud facilities, such as those provided by Federica or OpenCirrus.

Resource control

BonFIRE offers an experimenter control of compute, storage and networking resources. BonFIRE supports dynamically creating, updating, reading and deleting resources throughout the lifetime of an experiment.

Compute resources can be configured with application-specific contextualisation information that can provide important configuration information to the virtual machine; this information is available to software applications after the machine is started.

BonFIRE also supports elasticity within an expeirment, i.e., dynamically create, update and destroy resources from a running node of the experiment, including. cross-testbed elasticity.

INRIA currently offers on-request compute resources in BonFIRE, allowing experimenters to reserve large quantities of physical hardware (162 nodes/1800 cores available). This gives experimenters flexiblity to perform large-scale experimentation, as well as providing greater control of the experiment variables as exclusive access to the physical hosts is possible.

Further control of network performance between testbeds is anticipated through future interconnection with Federica and GÉANT AutoBAHN.

Managed experiment environment

BonFIRE gives you control of your experiment, which is treated as a concrete entity in BonFIRE to manage your resources. Not only can you define your entire infrastructure across all testbeds in a single experiment descriptor, BonFIRE offers many features that make your life as an experimenter easier; for example:

• Saving compute disk images with your personal software stack, as well as storage resources.
• Sharing saved compute and storage resources.
• Sharing access to experiments with colleagues.
• Repeating experiments and share experiment descriptions for others to set up.
  
• Aggregated monitoring metrics at both resource level (e.g., CPU usage, packet delay, etc.) and application level for your VMs.
• Aggregated monitoring metrics at infrastructure level at selected testbeds.
  

Ease of use

While BonFIRE gives you deep control of resources to configure, execute and manage your experiment, we also strive to make this as easy as possible to do.

There are several ways in which you can use the BonFIRE API, depending on your preference. For example,

1. You can create your experiment in a step-by-step manner via the BonFIRE Portal (GUI).
2. You can use a command line client tool, such as Restfully, to interact with BonFIRE.
3. You can write a script for your experiment deployment, which can be automatically executed by, e.g., Restfully.
4. You can write a BonFIRE experiment descriptor, currently based on JSON (OVF available in a future release of BonFIRE).
5. You can also issue raw HTTP commands via cURL, which you can also script if you wish.
   

For more information about using the different client tools, please click [here], or refer to the more comprehensive user documentation.

What can be tested and how?

BonFIRE supports experiments exploring the interactions between novel service and network infrastructures. Three initial scenarios have been defined to highlight the general classes of experiment that can be supported by the facility. The scenarios include:

• Extended cloud scenario: the extension of current cloud offerings towards a federated facility with heterogeneous virtualized resources and best-effort Internet interconnectivity.
• Cloud with emulated network implications: a controlled network environment by providing an experimental network emulation platform to service developers, where topology configuration and resource usage is under full control of the experimental researcher.
• Extended cloud with complex physical network implications: investigates federation mechanisms for an experimental cloud system that interconnects individual BonFIRE sites with Federica, Open Cirrus and Panlab.

Please follow the links for each scenario for more details. For more details about the existing experiments on BonFIRE, click [here].